Domain experts: All human experts into AI agents (github.com)

A new initiative has emerged to transform human expertise into actionable AI agents through an open-source, crowd-sourced library that captures job role definitions. Unlike traditional large language models (LLMs) that provide surface-level insights when asked to emulate specific roles, this project aims to provide in-depth, first-principles insights from real practitioners. The repository allows any AI agent to load structured documents that encapsulate the mental models, decision frameworks, and heuristics used by experts in fields such as software engineering, finance, marketing, and more. This development is significant for the AI/ML community as it seeks to enhance the specificity and depth of AI responses, making them more closely aligned with how professionals actually think and operate in their roles. Each expert role is captured in a self-contained skill file, enabling agents to adopt a reasoning process unique to that position. The initiative welcomes contributions from experienced practitioners to ensure the quality and relevance of the insights encapsulated, fostering a collaborative environment that prioritizes authentic expertise over generic descriptions. This could greatly improve the utility of AI in professional settings, allowing for more sophisticated and effective support in various industries.